Acoustic vehicle classification by fusing with semantic annotation

Current research on acoustic vehicle classification has been generally aimed at utilizing various feature extraction methods and pattern recognition techniques. Previous research in gait biometrics has shown that domain knowledge or semantic enrichment can assist in improving the classification accuracy. In this paper, we address the problem of semantic enrichment by learning the semantic attributes from the training set, and then formalize the domain knowledge by using ontologies. We first consider a simple data ontology, and discuss how to use it for classification. Next we propose a scheme, which uses a semantic attribute to mediate information fusion for acoustic vehicle classification. To assess the proposed approaches, experiments are carried out based on a data set containing acoustic signals from five types of vehicles. Results indicate that whether the above semantic enrichment can lead to improvement depends on the accuracy of semantic annotation. Among the two enrichment schemes, semantically mediated information fusion achieves less significant improvement, but is insensitive to the annotation error.

[1]  Denis McKeown,et al.  Vehicle classification by acoustic signature , 1998 .

[2]  Mark S. Nixon,et al.  Acoustic information fusion for ground vehicle classification , 2008, 2008 11th International Conference on Information Fusion.

[3]  Mark S. Nixon,et al.  Approaching Semantically-Mediated Acoustic Data Fusion , 2007, MILCOM 2007 - IEEE Military Communications Conference.

[4]  Volkan Cevher,et al.  Vehicle Speed Estimation Using Acoustic Wave Patterns , 2009, IEEE Transactions on Signal Processing.

[5]  Zehang Sun,et al.  On-road vehicle detection: a review , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Douglas E. Lake,et al.  Harmonic phase coupling for battlefield acoustic target identification , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[7]  Yu Hen Hu,et al.  Vehicle classification in distributed sensor networks , 2004, J. Parallel Distributed Comput..

[8]  B. R. Wilkins,et al.  The analysis of vehicle sounds for recognition , 1972, Pattern Recognit..

[9]  Robert I. Damper,et al.  A 'No Panacea Theorem' for classifier combination , 2008, Pattern Recognit..

[10]  Volkan Cevher,et al.  Joint Acoustic-Video Fingerprinting of Vehicles, Part I , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[11]  Mel Siegel,et al.  Vehicle sound signature recognition by frequency vector principal component analysis , 1999, IEEE Trans. Instrum. Meas..

[12]  M.S. Nixon,et al.  The Use of Semantic Human Description as a Soft Biometric , 2008, 2008 IEEE Second International Conference on Biometrics: Theory, Applications and Systems.

[13]  Mario E. Munich Bayesian subspace methods for acoustic signature recognition of vehicles , 2004, 2004 12th European Signal Processing Conference.

[14]  Jun-Wei Hsieh,et al.  Automatic traffic surveillance system for vehicle tracking and classification , 2006, IEEE Transactions on Intelligent Transportation Systems.

[15]  Gene T. Whipps,et al.  Multiple target tracking and classification improvement using data fusion at node level using acoustic signals , 2005, SPIE Defense + Commercial Sensing.

[16]  Tien Pham,et al.  Algorithm for classifying multiple targets using acoustic signatures , 2004, SPIE Defense + Commercial Sensing.

[17]  Jerry M. Mendel,et al.  Classification of Battlefield Ground Vehicles Using Acoustic Features and Fuzzy Logic Rule-Based Classifiers , 2007, IEEE Transactions on Fuzzy Systems.